© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1369
    Prev
    Next
    INDEX
    Explanations

    fight for survival or great sorrow

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on explicit numeric tokens or measurements (e.g. statistical figures, model numbers, page references) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.75
    -
    0.62
    /
    0.56
     your
    0.55
     when
    0.52
     such
    0.52
     you
    0.50
    ’
    0.49
     X
    0.48
     only
    0.46
    POSITIVE LOGITS
    ceti
    0.58
    Ordine
    0.58
    觫
    0.57
    <unused493>
    0.57
    㮔
    0.57
    lcii
    0.56
    <unused2101>
    0.56
     Colombeau
    0.55
     zahlreichen
    0.55
    neutrophiles
    0.55
    Activations Density 0.000%

    No Known Activations